Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming
arXiv:2310.05673 · doi:10.1016/j.revip.2025.100120
Abstract
In this article we examine recent developments in the research area concerning the creation of end-to-end models for the complete optimization of measuring instruments. The models we consider rely on differentiable programming methods and on the specification of a software pipeline including all factors impacting performance -- from the data-generating processes to their reconstruction and the extraction of inference on the parameters of interest of a measuring instrument -- along with the careful specification of a utility function well aligned with the end goals of the experiment. Building on previous studies originated within the MODE Collaboration, we focus specifically on applications involving instruments for particle physics experimentation, as well as industrial and medical applications that share the detection of radiation as their data-generating mechanism.
70 pages, 17 figures. To be submitted to journal
References in corpus (29)
- Multi-messenger Observations of a Binary Neutron Star Merger
- Gravitational Waves and Gamma-rays from a Binary Neutron Star Merger: GW170817 and GRB 170817A
- Giant Gamma-ray Bubbles from Fermi-LAT: AGN Activity or Bipolar Galactic Wind?
- Everything is Connected: Graph Neural Networks
- Readout technologies for directional WIMP Dark Matter detection
- CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
- SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks
- EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets
- PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
- Optimizing EDELWEISS detectors for low-mass WIMP searches
- Single-Shot Characterization of High Transformer Ratio Wakefields in Nonlinear Plasma Acceleration
- Phase Space Reconstruction from Accelerator Beam Measurements Using Neural Networks and Differentiable Simulations
- Snowmass2021 Cosmic Frontier: The landscape of low-threshold dark matter direct detection in the next decade
- Report of the Topical Group on Particle Dark Matter for Snowmass 2021
- Characterization of SABRE crystal NaI-33 with direct underground counting
- Reconstructing particles in jets using set transformer and hypergraph prediction networks
- Crilin: A CRystal calorImeter with Longitudinal InformatioN for a future Muon Collider
- Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks
- Transverse phase space tomography in the CLARA accelerator test facility using image compression and machine learning
- Integration of Neuromorphic AI in Event-Driven Distributed Digitized Systems: Concepts and Research Directions
- Improving ANAIS-112 sensitivity to DAMA/LIBRA signal with machine learning techniques
- The Mercedes water Cherenkov detector
- Benchmarking energy consumption and latency for neuromorphic computing in condensed matter and particle physics
- Four-Dimensional Emittance Measurements of Ultrafast Electron Diffraction Optics Corrected Up to Sextupole Order
- ILC Reference Design Report Volume 3 - Accelerator
- Recoil imaging for directional detection of dark matter, neutrinos, and physics beyond the Standard Model
- SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
- Reverse-Mode Automatic Differentiation of Compiled Programs
- Forward-Mode Automatic Differentiation of Compiled Programs